Font Size: a A A

A Multi-Biometric Method For Identity Verification Based On ECG And Fingerprints

Posted on:2020-12-27Degree:DoctorType:Dissertation
Country:ChinaCandidate:Full Text:PDF
GTID:1368330590473194Subject:Computer Science and Technology
Abstract/Summary:PDF Full Text Request
Traditional authentication tactics like passwords and smart cards are insufficient for personal authentication because they can be shared,forgotten,copied,manipulated or forged.Unlike the traditional methods,the biometric system,which is the science of recognizing an individual based on his/her physiological or behavioral traits is beginning to gain acceptance as a legitimate method for determining an individual's identity.Nowadays,biometrics are no longer confined to criminal law enforcement.In addition,more businesses use biometrics to regulate access to buildings and information.However,most of the unimodal biometrics suffer from limitations such as noisy data,non-universality and spoof attacks,which makes it not be able to achieve the performance requirements of real-world applications.To overcome these drawbacks of unimodal methods,we propose a novel secure multimodal biometric method which integrates electrocardiogram(ECG)with fingerprints using different combinations of fusion methods.Our method overcomes the limitations of both single methods,improve the performance of the overall method and enhance the security,as in this method we combine two characteristics,one is physical(fingerprint)and the other is vital(ECG)which offers the advantage of liveness detection to the method that makes the method robust to spoof attacks.Unlike other multimodal biometric methods that would be very inconvenient(e.g.a face,ear and fingerprint-based multimodal biometric system),the ECG signals can easily be acquired from fingers,which make the system very convenient and efficient.Moreover,ECG characteristics are suitable for human authentication as it provides the assurance of the aliveness of the person unlike other biometrics.Besides,fingerprints are one of the biometric authentication methods that have been widely used in many applications,and recently it gives acceptable accuracy for liveness detection.The first part of this thesis introduces the ECG and fingerprint as a unimodal biometric authentication system.In this part,we generated a novel cancelable ECG template for human authentication system based on two methods,improved Bio-Hashing and matrix operation,which are much secure than other cancelable methods.In addition,we proposed Q-Gaussian multi-class support vector machine(QG-MSVM)as a classifier for fingerprint authentication,which outperforms other comparing MSVM methods in terms of fingerprint classification accuracy.Finally,the performance of each method is presented at the end of this part.In the second part of this thesis,we propose a secure multimodal biometric method that uses convolution neural network(CNN)and QG-MSVM based on a different level fusion of ECG and fingerprint.Firstly,we propose two authentication methods with two different level fusion algorithms: feature level fusion and decision level fusion.The feature extraction for individual modalities is performed using CNN.In this step,we selected two layers from CNN that achieve the highest accuracy,in which each layer is regarded as separated feature descriptors.After that,we have combined between them using the proposed internal fusion to generate the biometric templates.In the next step,we have applied the improved Bio-Hashing technique to protect these templates and increase the security of the proposed method.In the authentication stage,we proposed QG-MSVM as a classifier for authentication to improve the performance.Secondly,we proposed a secure multimodal biometric method by fusing ECG and fingerprint based on CNN.The feature extraction for individual modalities is performed using CNN and then biometric templates are generated from these features.After that,we have applied the matrix operation technique to protect these templates.In the authentication stage,we proposed QG-MSVM as a classifier to improve the authentication performance.Finally,we used score level fusion to make the final decision.Our methods are tested on several publicly available databases for ECG and fingerprint.Experimental results show that the proposed multimodal methods are efficient,robust and reliable than existing multimodal authentication algorithms.According to the advantages of the proposed method,it can be deployed in real applications.
Keywords/Search Tags:Authentication, Biometrics, CNN, ECG, Fingerprint, Multimodal biometrics
PDF Full Text Request
Related items